Skip to content [0.6.22] - 2025-08-11
Added
- 🔗 OpenAI API '/v1' Endpoint Compatibility: Enhanced API compatibility by supporting requests to paths like '/v1/models', '/v1/embeddings', and '/v1/chat/completions'. This allows Open WebUI to integrate more seamlessly with tools that expect OpenAI's '/v1' API structure.
- 🪄 Toggle for Guided Response Regeneration Menu: Introduced a new setting in 'Interface' settings, providing the ability to enable or disable the expanded guided response regeneration menu. This offers users more control over their chat workflow and interface preferences.
- ✨ General UI/UX Enhancements: Implemented various user interface and experience improvements, including more rounded corners for cards in the Knowledge, Prompts, and Tools sections, and minor layout adjustments within the chat Navbar for improved visual consistency.
- 🌐 Localization & Internationalization Improvements: Introduced support for the Kabyle (Taqbaylit) language, refined and expanded translations for Chinese, expanding the platform's linguistic coverage.
Fixed
- 🐞 OpenAI Error Message Propagation: Resolved an issue where specific OpenAI API errors (e.g., 'Organization Not Verified') were obscured by generic 'JSONResponse' iterable errors. The system now correctly propagates detailed and actionable error messages from OpenAI to the user.
- 🌲 Pinecone Insert Issue: Fixed a bug that prevented proper insertion of items into Pinecone vector databases.
- 📦 S3 Vector Issue: Resolved a bug where s3vector functionality failed due to incorrect import paths.
- 🏠 Landing Page Option Setting Not Working: Fixed an issue where the landing page option in settings was not functioning as intended.